© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91329
    Prev
    Next
    INDEX
    Explanations

    followed by "based" or "derived"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     яку
    -0.99
    祈り
    -0.98
    Đặc
    -0.93
    izziness
    -0.92
    Vastaa
    -0.91
     腳
    -0.91
    場所で
    -0.90
    Karla
    -0.90
    uscitation
    -0.89
     accordé
    -0.88
    POSITIVE LOGITS
    based
    4.91
     based
    4.75
    BASED
    4.03
    Based
    3.95
     Based
    3.63
     BASED
    3.45
    基于
    2.45
     basada
    2.28
     основан
    2.14
     основе
    2.06
    Activations Density 0.359%

    No Known Activations